Use when writing or reviewing Java code in this repo that calls Deepgram Conversational STT v2 / Flux over `/v2/listen`. Covers `client.listen().v2().v2WebSocket()`, `V2ConnectOptions`, `onTurnInfo`, and turn-aware close handling. Use `deepgram-java-speech-to-text` for standard v1 transcription and `deepgram-java-voice-agent` for fully interactive assistants. Triggers include "flux", "conversational stt", "listen v2", "turn detection", "end of turn", and "eot".

Implement and verify joelclaw observability on every change so failures cannot stay silent. Use when adding/updating Inngest functions, gateway channels, webhook providers, APIs, workers, or any pipeline step. Enforces canonical OTEL contract, storage path, and verification gates. Triggers on: 'o11y', 'observability', 'logging', 'otel', 'instrument this', 'silent failure', 'add telemetry', 'log this function'.

Update and maintain joelclaw.com — the Next.js web app at apps/web/. Use when writing blog posts, editing pages, updating the network page, changing layout/header/footer, adding components, or fixing anything on the site. Hard content triggers: 'write article about X' (draft in Convex), 'publish article <slug>' (set draft=false + revalidate tags/paths). Also triggers on: 'update the site', 'write a post', 'fix the blog', 'joelclaw.com', 'update network page', 'add a page', 'change the header', or any task involving the public-facing web app.

Rebrand Atomic CRM — change the application logo (the wordmark in the header and on the login/signup pages) and/or the title/name. Use when the user wants to change, swap, update, or rebrand the CRM logo or title. Handles the two light/dark-mode logo variants, the three places the title is hardcoded, the config that points at them, and — optionally — the browser favicon and PWA app icons.

Deploys agent skill collections from any GitHub repository with a /skills folder to one or more distribution surfaces: GitHub releases, Claude Code marketplace, VS Code plugin marketplace, and Copilot CLI plugin marketplace. Handles pre-flight validation, conventional commit analysis, version bumping across surface configs, and surface-specific publishing with dry-run support. Use when releasing, publishing, or deploying a skills collection to any supported marketplace or creating a GitHub release for a skills repository. Don't use for deploying non-skill packages, npm modules, Docker images, or Azure resources.

Deploys agent skill collections from any GitHub repository with a /skills folder to one or more distribution surfaces: GitHub releases, Claude Code marketplace, VS Code plugin marketplace, and Copilot CLI plugin marketplace. Handles pre-flight validation, conventional commit analysis, version bumping across surface configs, and surface-specific publishing with dry-run support. Use when releasing, publishing, or deploying a skills collection to any supported marketplace or creating a GitHub release for a skills repository. Don't use for deploying non-skill packages, npm modules, Docker images, or Azure resources.

Set up a complete outbound email campaign in Smartlead. Asks the user for campaign goal, audience, messaging, schedule, and mailbox allocation. Creates the campaign, adds leads, saves email sequences, sets schedule, and assigns available mailboxes. Use when a user wants to launch email outreach via Smartlead.

Analyzes room observations to identify potential living things (e.g., eggs, plants, animals) among listed objects. Use this skill when a task involves finding, focusing on, or interacting with a living thing, biological entity, or organism. Processes observation text, flags candidate living items based on domain knowledge, and outputs a focused target for subsequent actions like focus on or pick up.

Use when the agent needs to find a specific object in ALFWorld that is not currently in inventory and whose location is unknown. This skill parses the environment observation, ranks receptacles by likelihood of containing the target object using common-sense reasoning, and outputs a navigation action to the most promising location.

Moves the agent to a specified receptacle or object location within the Alfworld environment. Use this skill when the agent needs to physically approach a target to inspect or interact with it, such as when checking an object's state or preparing for pickup. The skill takes a target location name as input and executes the 'go to' action, resulting in the agent being positioned at the destination for subsequent operations.

Use when an agent folder must pass the Agentlas Cloud 2-stage security scan (static rules + BYOK LLM judgment) before private sync or public publish, or when asked to run/interpret `hephaestus security scan`.

Use when designing a new multi-agent team, visible agents folder, role boundaries, handoff flow, PM Soul, Memory Curator, Policy Gate, or evaluation role. Use for agent-team repo creation even when the user only says they want a meta-agent or agent operating system.

Prepare and publish a new version of the waza azd extension. USE FOR: "publish extension", "release new version", "bump version", "prepare release", "update changelog", "azd publish", "new release", "version bump", "cut a release". DO NOT USE FOR: running evals (use waza), writing skills (use skill-authoring), CI/CD pipeline changes (edit workflow files directly).

Build, debug, or publish an OpenClacky extension — scaffold a new one from an idea, fix a broken/invisible panel/api/skill/agent, or ship it to the marketplace. Trigger on create/start extension, plugin, panel, ext verify error, "won't load", "not showing up", publish/ship/unpublish an extension.

Load built-in CausalPy example datasets for demos, tutorials, tests, and quick causal-analysis prototypes. Use when the user needs sample data or asks which demo datasets are available.

Urizen — an AI equity-research desk + the first autonomous fund on Robinhood Chain (4663), as an agent skill. Real charts & technicals for any tokenized US stock, SEC fundamentals + filings + insider activity, Wall Street analyst consensus, financial news, the macro calendar (Fed/CPI/jobs), live prediction-market odds, and on-chain price — plus the fund's live strategies, book, execution tape, and one-token exposure via $URI. Public, key-less, CORS-open REST on chain 4663. Triggers on: "urizen", "research a stock", "tokenized stock", "SEC fundamentals", "analyst rating", "economic calendar", "prediction market odds", "copy trade the fund", "urizen book", "buy $URI".

Track legislation, regulatory actions, and legal developments affecting prediction markets, crypto, and AI agents. Per item: stage (Rumor / Proposed / Comment / Final / Enforced), impact (kills the category / structural change / disclosure burden / noise), affected protocols by name, and a concrete operator action. Use as pre-trade context on legally-wrapped assets. Triggers: "what's happening in crypto reg", "track CFTC actions", "prediction market regulation", "new SEC rules", "AI agent compliance updates".

Validate the output of any installed skill against an assertion manifest — word counts, required patterns, forbidden phrases, required sections, source citation. Detects regressions by diffing vs prior runs (NEW_FAIL / NEW_PASS / CHRONIC / STABLE_FAIL). Bootstrap mode generates a starter manifest from a skill's recent successful runs so manifests aren't written speculatively. Triggers: "evaluate this skill's output", "check skill X for regressions", "bootstrap evals for Y", "did this skill output pass quality gates".

Generate a concise, shareable code snippet URL for code.franciscomoretti.com. Use when preparing a code image or short snippet for Twitter, X, social sharing, or a presentation.

Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform. Each writer exports a function that accepts a config interface, creates directories (rules/, skills/, mcp configs), writes files with proper formatting and frontmatter, and returns string[] of written file paths. Use when adding platform support for a new agent, integrating a new code AI tool, or extending caliber to support new targets. Do NOT use for modifying existing writers, refactoring scoring logic, or changing how writers are invoked.